Invented by Yerby; Dennis W., Ankita; FNU, Truist Bank

The world of digital engagement is growing fast. Companies want to connect with users in ways that are more personal and helpful. This new patent application describes a smart system that watches how people use their devices and finds out when they might be interested in games or other fun apps. When the time is right, the system sends them a signal with information about a game or app they might enjoy. This article will help you understand why this idea matters, how it builds on past work, and what makes it special.

Background and Market Context

Today, people spend a lot of time using their phones, computers, and tablets. They check emails, pay bills, shop online, watch videos, and play games. Companies want to reach these users with the right message at the right time. They want to offer games and other fun apps, but they do not want to annoy people with ads they do not care about. Instead, they need a way to know when someone is likely to want a new game or app and send them a message just then.

Gaming is not just about fun anymore. It is also used to teach people new things. For example, banks might use games to teach customers how to save money or invest. These games can help users build good habits while having fun. But for these games and apps to work, companies need to find the people who are most likely to enjoy them. Sending messages to everyone is wasteful and can upset customers. The goal is to make sure the right people get the right message at the right time.

Digital technology has changed the way companies collect and use information. In the past, most records were on paper. Now, almost everything is digital. That means companies have more information about what people do online. This is good because it helps companies learn about their users. But it can also be overwhelming. There is so much data that it is hard to know what matters most. Companies need smart tools to help them find patterns and make sense of all the information.

The market for digital games and apps is huge. There are thousands of options, from simple puzzles to big, online worlds. Many companies use games to connect with customers, teach them about products, or just offer a fun break. But with so many choices, users can get lost. Companies need ways to stand out and reach people who are ready for something new.

This is where the new patent application comes in. It describes a system that watches for special moments when a user might want a game or app. The system does not guess. It uses smart computer programs to find patterns in how people use their devices. When it finds someone who is likely to be interested, it sends them a message with information about a game or app. This helps companies connect with users in a way that feels personal and timely.

The need for this kind of system is clear. Users want helpful suggestions, not spam. Companies want to use their resources wisely, reaching people who will be happy to hear from them. As more people use digital devices for all parts of their life, the value of smart, targeted signals only grows.

Scientific Rationale and Prior Art

The system in the patent is based on ideas from computer science and artificial intelligence. The main goal is to look at what users do on their devices and find patterns that show when they might want a new game or app. This is not a new idea by itself. For years, companies have tried to predict what customers want using things like loyalty cards, surveys, and simple computer programs.

Older systems often used rules made by people. For example, if someone bought a toy, the system might suggest another toy. If someone played one game, it might suggest a similar game. These systems worked, but they were simple and often missed the mark. They could not handle the huge amount of data that comes from modern digital life.

As technology got better, companies started using machine learning. Machine learning is when computers look at lots of data and learn to make predictions. For example, a computer might learn that people who play puzzle games at night often want new games on weekends. Or it might notice that people who pay bills online are interested in financial games. These systems are better than old rule-based systems, but they still have limits. Some only look at what users do in one app or on one website. Others only use data from one company. Many do not look for the deeper patterns that show real interest.

There have also been systems that send messages to users when certain things happen. For example, some apps send reminders or suggest new features after a user finishes a task. Some marketing tools send emails when someone visits a website or puts something in a shopping cart. But these signals are often based on simple triggers and may not always be welcome.

What makes this patent application different is how it looks for special patterns called “digital diversion attributes.” This means the system tries to find out when a user is ready for a break or a new activity, like playing a game. It does this by tracking not just what the user does, but also the resources they use (like money or time), and how those resources go up or down. For example, if someone gets paid, spends money, or makes a lot of online transactions, the system might notice patterns that match people who enjoy certain games or apps.

Another key difference is the use of advanced machine learning, including neural networks. Neural networks are computer programs inspired by the human brain. They can find very complex patterns that are hard for people or simple programs to see. The system uses these tools to learn from both “positive” and “negative” examples. Positive examples are users who really do want the game or app. Negative examples are those who are not interested. By learning from both, the system gets better at knowing who to contact and when.

The patent also describes using a “contact trajectory.” This is a way of tracking the path a user takes as they do things online. The system uses this path to decide the best time to send a message. If the system thinks a user is very likely to want the game or app, and if they are not already using it, it sends a message. This approach is smarter and more focused than older systems.

In summary, while some parts of this idea have appeared before (like targeted marketing and machine learning), the combination and depth of analysis are new. The system goes beyond basic triggers or simple user actions. It uses advanced AI to find the best moments to contact users, making it more likely that the message will be welcome and useful.

Invention Description and Key Innovations

This patent application describes a system that is both smart and careful about how it connects users with new games or apps. Let’s break down how it works in clear steps, using simple words.

First, there is a main computer system. This system is run by a company (called the “first entity”). The main computer connects to many user devices, like phones, tablets, or computers, over the internet. Each user has their own digital profile and history.

The system pays attention to “event signals.” These are things that happen on the user’s device, like logging in, spending money, getting paid, playing a game, or using an app. Every event is recorded as an “input” (something the user gets) or an “output” (something the user gives or spends). For example, if you deposit money into your bank account, that’s an input event. If you buy something online, that’s an output event.

Each event is turned into a record with numbers. For example, how much money was spent, when it happened, what kind of app was used, and so on. The system keeps track of these numbers over time for each user.

The smart part of the system is how it looks for “digital diversion attributes.” This means it tries to spot signs that the user is ready for a fun new activity, like playing a game. To do this, the system uses artificial intelligence—specifically, machine learning models like neural networks. These models are trained using real data, learning what patterns are common among people who like certain games or apps.

The models are not just looking at one thing. They look at many factors: how often users play games, how much they spend, what times of day they are most active, and even what kinds of tasks they complete. They also learn from both users who are interested and those who are not, which helps avoid mistakes.

The system then builds a “contact trajectory” for each user. This is like a digital path showing what the user has done and where they might be headed next. If the system thinks the user is likely to be interested in a new game or app, it checks if the user is already using it. If not, it gets ready to send a signal.

But the system does not send messages to everyone. It sets a “threshold.” Only users who score high enough—meaning they are very likely to be interested—get a message. This message might be information about a new game, a link to download it, or an invitation to play. The message is sent directly to the user’s device, so it shows up at the right time.

Sometimes, before sending the message, the system checks again to make sure the user is not already using the app. This helps avoid sending repeats or annoying the user. The system can also notify company staff or agents if a user seems like a very good fit, so a person can follow up if needed.

What makes this invention special is how everything works together:

– The system tracks both inputs and outputs for each user, building a rich profile.
– It uses advanced AI, not just simple rules, to find complex patterns.
– It looks for the right “moment” based on the user’s digital path.
– It only sends signals to users who are most likely to be interested, based on a clear threshold.
– It avoids sending duplicate messages to users who already have the app.
– It can personalize not just the message, but also the timing and delivery.

This approach saves time and money for companies, reduces unwanted messages for users, and makes it more likely that users will enjoy the games or apps they are shown. By learning and adapting over time, the system keeps getting better at finding the right users and the right moments.

In real use, this system could help banks offer games that teach people how to save or invest. It could help online stores suggest fun apps during shopping breaks. It could even help health companies offer wellness games after users finish a workout. The key is that the system is always learning, always careful, and always trying to connect users with things they will like, right when they are most open to it.

This is much more than a simple ad system. It’s a smart, learning assistant that helps companies and users find the best fit at the best time, without being pushy or wasteful.

Conclusion

The patent application described here introduces a new way for companies to connect with users. By carefully watching how people use their devices and applying smart AI models, the system finds the best moments to offer games or apps. This helps users find fun, useful tools when they want them, and helps companies use their resources wisely. The system’s careful approach—using advanced learning, deep profiles, and smart timing—sets it apart from older, less personal methods. As technology keeps growing, systems like this will be key to making digital experiences more friendly, helpful, and engaging for everyone.

Click here https://ppubs.uspto.gov/pubwebapp/ and search 20250218248.